read_contract

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already indicate readOnly, destructive=false, idempotent, openWorld. The description adds critical behavioral traits: it follows proxies once, refuses non-view/pure functions, fetches ABI from Etherscan or requires inline ABI, validates types via viem. No contradictions; the description enriches transparency significantly.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is thorough and well-structured, starting with a clear one-line summary. It covers many edge cases without being overly verbose. A slight reduction in examples could improve conciseness, but overall it is efficient and front-loaded.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's complexity (5 parameters, 2 required, no output schema), the description covers inputs, behavior, and restrictions thoroughly. It omits explicit return value format, but since the return is dynamic (function-dependent), this is acceptable. Provides sufficient context for an AI to use the tool correctly.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 80%, but the description adds substantial meaning: explains ABI fetching options, function name disambiguation (full signature), argument type formatting with examples (decimal strings for uint256, hex for bytes32, addresses), and the `abi` parameter's override purpose. This goes well beyond the schema defaults and patterns.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states it is a read-only tool for calling view/pure functions on EVM contracts, with explicit examples and a direct distinction from the write sibling `prepare_custom_call`. It covers the exact resource (contract state) and verb (read via function call), leaving no ambiguity.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description explicitly guides when to use (long tail of on-chain reads not covered by protocol-specific tools) and when not to (state-changing functions, unverified contracts without ABI). It provides alternative tool (`prepare_custom_call`) for writes, and offers detailed guidance on function disambiguation and argument formatting.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.